Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,40 @@
+---
+license: other
+library_name: transformers
+tags:
+- mlx
+widget:
+- text: '<start_of_turn>user
+
+    How does the brain work?<end_of_turn>
+
+    <start_of_turn>model
+
+    '
+inference:
+  parameters:
+    max_new_tokens: 200
+extra_gated_heading: Access Gemma on Hugging Face
+extra_gated_prompt: To access Gemma on Hugging Face, you’re required to review and
+  agree to Google’s usage license. To do this, please ensure you’re logged-in to Hugging
+  Face and click below. Requests are processed immediately.
+extra_gated_button_content: Acknowledge license
+license_name: gemma-terms-of-use
+license_link: https://ai.google.dev/gemma/terms
+---
+
+# sugatoray/mlx-gemma-2b-it-q4bits
+This model was converted to MLX format from [`google/gemma-2b-it`]().
+Refer to the [original model card](https://huggingface.co/google/gemma-2b-it) for more details on the model.
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("sugatoray/mlx-gemma-2b-it-q4bits")
+response = generate(model, tokenizer, prompt="hello", verbose=True)
+```

config.json

@@ -0,0 +1,86 @@
+{
+    "vocab_size": 256000,
+    "max_position_embeddings": 8192,
+    "hidden_size": 2048,
+    "intermediate_size": 16384,
+    "num_hidden_layers": 18,
+    "num_attention_heads": 8,
+    "head_dim": 256,
+    "num_key_value_heads": 1,
+    "hidden_act": "gelu",
+    "initializer_range": 0.02,
+    "rms_norm_eps": 1e-06,
+    "use_cache": true,
+    "rope_theta": 10000.0,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "return_dict": true,
+    "output_hidden_states": false,
+    "output_attentions": false,
+    "torchscript": false,
+    "torch_dtype": "bfloat16",
+    "use_bfloat16": false,
+    "tf_legacy_loss": false,
+    "pruned_heads": {},
+    "tie_word_embeddings": true,
+    "chunk_size_feed_forward": 0,
+    "is_encoder_decoder": false,
+    "is_decoder": false,
+    "cross_attention_hidden_size": null,
+    "add_cross_attention": false,
+    "tie_encoder_decoder": false,
+    "max_length": 20,
+    "min_length": 0,
+    "do_sample": false,
+    "early_stopping": false,
+    "num_beams": 1,
+    "num_beam_groups": 1,
+    "diversity_penalty": 0.0,
+    "temperature": 1.0,
+    "top_k": 50,
+    "top_p": 1.0,
+    "typical_p": 1.0,
+    "repetition_penalty": 1.0,
+    "length_penalty": 1.0,
+    "no_repeat_ngram_size": 0,
+    "encoder_no_repeat_ngram_size": 0,
+    "bad_words_ids": null,
+    "num_return_sequences": 1,
+    "output_scores": false,
+    "return_dict_in_generate": false,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "remove_invalid_values": false,
+    "exponential_decay_length_penalty": null,
+    "suppress_tokens": null,
+    "begin_suppress_tokens": null,
+    "architectures": [
+        "GemmaForCausalLM"
+    ],
+    "finetuning_task": null,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
+    "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+    },
+    "tokenizer_class": null,
+    "prefix": null,
+    "bos_token_id": 2,
+    "pad_token_id": 0,
+    "eos_token_id": 1,
+    "sep_token_id": null,
+    "decoder_start_token_id": null,
+    "task_specific_params": null,
+    "problem_type": null,
+    "_name_or_path": "/Users/sugatoray/.cache/huggingface/hub/models--google--gemma-2b-it/snapshots/9f5abd187467338b36f75c06bf2bda7b2e7eb404",
+    "transformers_version": "4.38.1",
+    "model_type": "gemma",
+    "rope_scaling": null,
+    "quantization": {
+        "group_size": 64,
+        "bits": 4
+    }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0b7326ef70120724b1d6912d7d16a530821bce6e25a6826baef58123dfb6d5c
+size 2163541255

model.safetensors.index.json

@@ -0,0 +1,423 @@
+{
+    "metadata": {
+        "total_size": 2163494912
+    },
+    "weight_map": {
+        "model.embed_tokens.weight": "model.safetensors",
+        "model.layers.0.input_layernorm.weight": "model.safetensors",
+        "model.layers.0.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.0.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.0.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.0.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.0.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.0.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.0.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.0.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.0.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.0.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.0.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.0.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.0.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.0.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.1.input_layernorm.weight": "model.safetensors",
+        "model.layers.1.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.1.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.1.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.1.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.1.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.1.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.1.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.1.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.1.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.1.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.1.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.1.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.1.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.1.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.10.input_layernorm.weight": "model.safetensors",
+        "model.layers.10.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.10.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.10.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.10.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.10.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.10.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.10.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.10.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.10.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.10.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.10.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.10.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.10.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.10.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.11.input_layernorm.weight": "model.safetensors",
+        "model.layers.11.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.11.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.11.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.11.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.11.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.11.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.11.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.11.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.11.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.11.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.11.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.11.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.11.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.11.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.12.input_layernorm.weight": "model.safetensors",
+        "model.layers.12.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.12.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.12.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.12.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.12.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.12.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.12.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.12.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.12.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.12.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.12.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.12.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.12.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.12.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.13.input_layernorm.weight": "model.safetensors",
+        "model.layers.13.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.13.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.13.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.13.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.13.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.13.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.13.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.13.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.13.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.13.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.13.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.13.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.13.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.13.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.14.input_layernorm.weight": "model.safetensors",
+        "model.layers.14.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.14.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.14.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.14.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.14.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.14.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.14.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.14.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.14.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.14.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.14.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.14.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.14.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.14.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.15.input_layernorm.weight": "model.safetensors",
+        "model.layers.15.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.15.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.15.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.15.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.15.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.15.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.15.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.15.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.15.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.15.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.15.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.15.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.15.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.15.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.16.input_layernorm.weight": "model.safetensors",
+        "model.layers.16.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.16.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.16.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.16.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.16.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.16.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.16.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.16.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.16.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.16.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.16.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.16.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.16.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.16.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.17.input_layernorm.weight": "model.safetensors",
+        "model.layers.17.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.17.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.17.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.17.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.17.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.17.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.17.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.17.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.17.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.17.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.17.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.17.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.17.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.17.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.2.input_layernorm.weight": "model.safetensors",
+        "model.layers.2.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.2.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.2.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.2.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.2.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.2.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.2.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.2.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.2.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.2.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.2.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.2.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.2.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.2.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.3.input_layernorm.weight": "model.safetensors",
+        "model.layers.3.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.3.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.3.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.3.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.3.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.3.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.3.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.3.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.3.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.3.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.3.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.3.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.3.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.3.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.4.input_layernorm.weight": "model.safetensors",
+        "model.layers.4.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.4.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.4.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.4.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.4.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.4.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.4.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.4.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.4.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.4.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.4.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.4.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.4.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.4.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.5.input_layernorm.weight": "model.safetensors",
+        "model.layers.5.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.5.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.5.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.5.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.5.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.5.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.5.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.5.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.5.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.5.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.5.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.5.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.5.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.5.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.6.input_layernorm.weight": "model.safetensors",
+        "model.layers.6.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.6.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.6.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.6.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.6.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.6.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.6.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.6.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.6.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.6.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.6.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.6.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.6.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.6.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.7.input_layernorm.weight": "model.safetensors",
+        "model.layers.7.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.7.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.7.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.7.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.7.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.7.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.7.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.7.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.7.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.7.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.7.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.7.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.7.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.7.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.8.input_layernorm.weight": "model.safetensors",
+        "model.layers.8.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.8.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.8.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.8.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.8.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.8.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.8.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.8.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.8.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.8.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.8.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.8.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.8.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.8.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
+        "model.layers.9.input_layernorm.weight": "model.safetensors",
+        "model.layers.9.mlp.down_proj.biases": "model.safetensors",
+        "model.layers.9.mlp.down_proj.scales": "model.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model.safetensors",
+        "model.layers.9.mlp.gate_proj.biases": "model.safetensors",
+        "model.layers.9.mlp.gate_proj.scales": "model.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model.safetensors",
+        "model.layers.9.mlp.up_proj.biases": "model.safetensors",
+        "model.layers.9.mlp.up_proj.scales": "model.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
+        "model.layers.9.self_attn.k_proj.biases": "model.safetensors",
+        "model.layers.9.self_attn.k_proj.scales": "model.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
+        "model.layers.9.self_attn.o_proj.biases": "model.safetensors",
+        "model.layers.9.self_attn.o_proj.scales": "model.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
+        "model.layers.9.self_attn.q_proj.biases": "model.safetensors",
+        "model.layers.9.self_attn.q_proj.scales": "model.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
+        "model.layers.9.self_attn.v_proj.biases": "model.safetensors",
+        "model.layers.9.self_attn.v_proj.scales": "model.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model.safetensors",
+        "model.norm.weight": "model.safetensors"
+    }
+}

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05e97791a5e007260de1db7e1692e53150e08cea481e2bf25435553380c147ee
+size 17477929

tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}